Robust Model-Based Fault Diagnosis for PEM Fuel Cell Air-Feed System

In this paper, the design of a nonlinear observer-based fault diagnosis approach for polymer electrolyte membrane (PEM) fuel cell air-feed systems is presented, taking into account a fault scenario of sudden air leak in the air supply manifold. Based on a simplified nonlinear model proposed in the literature, a modified super-twisting (ST) sliding mode algorithm is employed to the observer design. The proposed ST observer can estimate not only the system states, but also the fault signal. Then, the residual signal is computed online from comparisons between the oxygen excess ratio obtained from the system model and the observer system, respectively. Equivalent output error injection using the residual signal is able to reconstruct the fault signal, which is critical in both fuel cell control design and fault detection. Finally, the proposed observer-based fault diagnosis approach is implemented on the MATLAB/Simulink environment in order to verify its effectiveness and robustness in the presence of load variation.